• Journal of Information Processing Systems
• /
• v.16 no.6
• /
• pp.1250-1260
• /
• 2020

This study proposes a novel deep neural network model that can accurately detect objects and their relationships in an image and represent them as a scene graph. The proposed model utilizes several multimodal features, including linguistic features and visual context features, to accurately detect objects and relationships. In addition, in the proposed model, context features are embedded using graph neural networks to depict the dependencies between two related objects in the context feature vector. This study demonstrates the effectiveness of the proposed model through comparative experiments using the Visual Genome benchmark dataset.

• Journal of international Conference on Electrical Machines and Systems
• /
• v.3 no.2
• /
• pp.215-221
• /
• 2014

To satisfy the high voltage direct current (HVDC) grid connection demand for wind power generation system, a novel topology and control strategy of HVDC grid connection for open-winding permanent magnet synchronous generator (PMSG) based wind power generation system is proposed, in which two generator-side converter and two isolated DC/DC converters are used to transmit the wind energy captured by open winding PMSG to HVDC grid. By deducing the mathematic model of open winding PMSG, the vector control technique, position sensorless operation, and space vector modulation strategy is applied to implement the stable generation operation of PMSG. Finally, the simulation model based on MATLAB is built to validate the availability of the proposed control strategy.

• Bulletin of the Korea Photovoltaic Society
• /
• v.4 no.2
• /
• pp.45-53
• /
• 2018

Natural gas demand for power generation continued to increase until 2013 due to the expansion of large-scale LNG power plants after the black-out of 2011. However, natural gas demand for power generation has decreased sharply due to the increase of nuclear power and coal power generation. But demand for power generation has increased again as energy policies have changed, such as reducing nuclear power and coal power plants, and abnormal high temperatures and cold waves have occurred. If the gas pipeline pressure can be properly maintained by predicting these fluctuations, it can contribute to enhancement of operation efficiency by minimizing the operation time of facilities required for production and supply. In this study, we have developed a regression model with daily power demand and base power generation capacity as explanatory variables considering characteristics by day of week. The model was constructed using data from January 2013 to December 2016, and it was confirmed that the error rate was 4.12% and the error rate in the 90th percentile was below 8.85%.

• The Transactions of The Korean Institute of Electrical Engineers
• /
• v.61 no.10
• /
• pp.1548-1553
• /
• 2012

The important requirement for microgrid operation is to meet the balance between supply and demand. To meet, Combined Heat and Power (CHP) generation should be considered in microgrid scheduling. CHP generation is economical on the side of a consumer because it products heat and power. Therefore, it is high efficient. This paper presents a mathematical model for optimal microgrid operation including CHP generation using the optimal ratio of heat and power due to demand. The objective function and constraints are modeled by linear program (LP). Through the case study, the validation of the proposed model is shown.

• Proceedings of the KIEE Conference
• /
• 2005.07a
• /
• pp.775-777
• /
• 2005

In this paper, effects of the subsidy in the electricity market on the market equilibrium are analyzed. The generation competition markets are considered as the basic market structure. The market equilibrium with Cournot game model is derived, first. Then, the variation of Nash equilibrium is investigated when the subsidies to generation companies are provided. The market equilibrium with the subsidy in the electricity market, which is equivalent to the subgame perfect equilibrium, is analytically derived using Stackelberg game model and backward induction method. From this, how the provisions of subsidy to generation companies can affect the strategic behaviors of the generation companies and corresponding market equilibrium are explored, in this paper. Numerical examples are provided to illustrate the basic idea of this paper.

• Proceedings of the Korean Society of Precision Engineering Conference
• /
• 2002.10a
• /
• pp.1037-1040
• /
• 2002

In micro-stereolithography technology, fabrication conditions that include laser power, laser scan speed, laser scan pitch, and material property of photopolymer such as penetration depth and critical exposure are considered as major process variables. But the existing scan path generation methods based only on CAD model have not taken them into account, which has resulted in cross-section dimension of low accuracy. Thus, to enhance cross-section dimensional accuracy, the physical resin solidification n phenomena should be reflected in laser scan path generation and stage operating code. In this paper, multi-line experiments based on single line solidification model are performed. And the method for improving cross-section dimensional accuracy is presented, which is to apply the database based on experimental results to laser scan path generation.

• The Journal of Korea Robotics Society
• /
• v.5 no.3
• /
• pp.224-230
• /
• 2010

As robots are no longer just working labors in the industrial fields, but stepping into the human's daily lives, interaction and communication between human and robot is becoming essential. For this social interaction with humans, emotion generation of a robot has become necessary, which is a result of very complicated process. Concept of mood has been considered in psychology society as a factor that effects on emotion generation, which is similar to emotion but not the same. In this paper, mood factors for robot considering not only the conditions of the robot itself but also the circumstances of the robot are listed, chosen and finally considered as elements defining a 2-dimensional mood space. Moreover, architecture that combines the proposed mood model and a emotion generation module is given at the end.

• KIEE International Transactions on Power Engineering
• /
• v.12A no.1
• /
• pp.31-35
• /
• 2002

This paper presents a new operation scheme of UPFC to minimize both generation costs and active power losses in a normal operation state of power system. In a normal operation, cost minimization is a matter of primary concern among operating objectives. This paper considers two kinds of costs, generation costs and transmission losses. The total generation cost of active powers can be minimized by optimal power flow, and active power losses in the transmission system can be also minimized by power flow control of UPFC incorporated with minimization of generation costs. In order to determine amounts of active power reference of each UPFC required for the cost minimization, an iterative optimization algorithm based on the power flow calculation using the decoupled UPFC model is proposed. For verification of the proposed method, intensive studies have been performed on a 3-unit 6-bus system equipped with a UPFC.

• Journal of Electrical Engineering and Technology
• /
• v.8 no.4
• /
• pp.675-685
• /
• 2013

Generation capacities and transmission line constraints in a competitive electricity market make it troublesome to compute Nash Equilibrium (NE) for analyzing participants' strategic generation quantities. The NE can cause a mixed strategy NE rather than a pure strategy NE resulting in a more complicated computation of NE, especially in a multiplayer game. A two-level hierarchical optimization problem is used to model competition among multiple participants. There are difficulties in using a mathematical programming approach to solve a mixed strategy NE. This paper presents heuristics applied to the mathematical programming method for dealing with the constraints on generation capacities and transmission line flows. A new formulation based on the heuristics is provided with a set of linear and nonlinear equations, and an algorithm is suggested for using the heuristics and the newly-formulated equations.

• Journal of Advanced Navigation Technology
• /
• v.21 no.6
• /
• pp.643-650
• /
• 2017

Photovoltaic generation which has unlimited energy sources are very intermittent because they depend on the weather. Therefore, it is necessary to get accurate generation prediction with reducing the uncertainty of photovoltaic generation and improvement of the economics. The Meteorological Agency predicts weather factors for three days, but doesn't predict the sunshine and solar radiation that are most correlated with the prediction of photovoltaic generation. In this study, we predict sunshine and solar radiation using weather, precipitation, wind direction, wind speed, humidity, and cloudiness which is forecasted for three days at Meteorological Agency. The photovoltaic generation forecasting model is proposed by using predicted solar radiation and sunshine. As a result, the proposed model showed better results in the error rate indexes such as MAE, RMSE, and MAPE than the model that predicts photovoltaic generation without radiation and sunshine. In addition, DNN showed a lower error rate index than using SVM, which is a type of machine learning.